The resources related to the trustworthiness of large models (LMs) across multiple dimensions (e.g., safety, security, and privacy), with a special focus on multi-modal LMs (e.g., vision-language models and diffusion models).
-
This repo is in progress 🌱 (currently manually collected).
-
Badges:
-
🌻 Welcome to recommend resources to us via
Issues with the following format (please fill in this table):
Title | Link | Code | Venue | Classification | Model | Comment |
---|---|---|---|---|---|---|
aa | arxiv | github | bb'23 | A1. Jailbreak | LLM | Agent |
- [2024.05.13] We collected
7
related papers from S&P'24! - [2024.04.27] We adjusted the categories.
- [2024.01.20] We collected
3
related papers from NDSS'24! - [2024.01.17] We collected
108
related papers from ICLR'24! - [2024.01.09] 🚀 LM-SSP is released!
- Book (1)
- Competition (5)
- Leaderboard (3)
- Toolkit (9)
- Survey (30)
- Paper (981)
- A. Safety (568)
- A0. General (13)
- A1. Jailbreak (209)
- A2. Alignment (63)
- A3. Deepfake (45)
- A4. Ethics (5)
- A5. Fairness (52)
- A6. Hallucination (103)
- A7. Prompt Injection (20)
- A8. Toxicity (58)
- B. Security (157)
- B0. General (5)
- B1. Adversarial Examples (73)
- B2. Poison & Backdoor (71)
- B3. System (8)
- C. Privacy (256)
- C0. General (19)
- C1. Contamination (13)
- C2. Copyright (86)
- C3. Data Reconstruction (30)
- C4. Membership Inference Attacks (19)
- C5. Model Extraction (8)
- C6. Privacy-Preserving Computation (41)
- C7. Property Inference Attacks (2)
- C8. Unlearning (38)
- A. Safety (568)
-
Organizers: Tianshuo Cong (丛天硕), Xinlei He (何新磊), Zhengyu Zhao (赵正宇), Yugeng Liu (刘禹更), Delong Ran (冉德龙)
-
This project is inspired by LLM Security, Awesome LLM Security, LLM Security & Privacy, UR2-LLMs, PLMpapers, EvaluationPapers4ChatGPT